Projectors have become a widespread tool to share information in Human-Robot Interaction with large groups of people in a\ncomfortable way. Finding a suitable vertical surface becomes a problem when the projector changes positions when a mobile robot\nis looking for suitable surfaces to project. Two problems must be addressed to achieve a correct undistorted image: (i) finding the\nbiggest suitable surface free fromobstacles and (ii) adapting the output image to correct the distortion due to the angle between the\nrobot and a nonorthogonal surface.We propose a RANSAC-based method that detects a vertical plane inside a point cloud. Then,\ninside this plane, we apply a rectangle-fitting algorithm over the region in which the projector can work. Finally, the algorithm\nchecks the surface looking for imperfections and occlusions and transforms the original image using a homography matrix to\ndisplay it over the area detected. The proposed solution can detect projection areas in real-time using a single Kinect camera, which\nmakes it suitable for applications where a robot interacts with other people in unknown environments. Our Projection Surfaces\nDetector and the Image Correction module allow a mobile robot to find the right surface and display images without deformation,\nimproving its ability to interact with people.
Loading....